A Flexible Generative Model for Heterogeneous Tabular EHR with Missing Modality

Realistic synthetic electronic health records (EHRs) can be leveraged to accelerate methodological developments for research purposes while mitigating privacy concerns associated with data sharing. However, the training of Generative Adversarial Networks remains challenging, often resulting in issues like mode collapse. While diffusion models have demonstrated progress in generating quality synthetic samples for tabular EHRs given ample denoising steps, their performance wanes when confronted with missing modalities in heterogeneous tabular EHRs data. For example, some EHRs contain solely static measurements, and some contain only contain temporal measurements, or a blend of both data types. To bridge this gap, we introduce FLEXGEN-EHR-a versatile diffusion model tailored for heterogeneous tabular EHRs, equipped with the capability of handling missing modalities in an integrative learning framework. We define an optimal transport module to align and accentuate the common feature space of heterogeneity of EHRs. We empirically show that our model consistently outperforms existing state-of-the-art synthetic EHR generation methods both in fidelity by up to 3.10% and utility by up to 7.16%. Additionally, we show that our method can be successfully used in privacy-sensitive settings, where the original patient-level data cannot be shared.